Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate the end of thoughts or sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranean
    -0.57
    lavia
    -0.56
    ыре
    -0.55
     they
    -0.55
     California
    -0.54
     Engle
    -0.54
     They
    -0.54
    ​=
    -0.54
     He
    -0.53
     people
    -0.52
    POSITIVE LOGITS
     furthermore
    0.91
     således
    0.91
    withstanding
    0.90
     Accordingly
    0.89
     ciertamente
    0.89
    Примеча
    0.87
     indeed
    0.87
     moreover
    0.86
     accordingly
    0.86
     Needless
    0.85
    Act Density 0.603%

    No Known Activations